Efficient Offline Preference-Based Reinforcement Learning with Transition-Dependent Discounting
ICLR 2024（2024）
关键词
preference-based reinforcement learning,offline reinforcement learning,RLHF,transition-dependent discounting
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要